Qing Guo
YOU?
Author Swipe
View article: Benchmarking Drag⋆ for eye direction transformation and beyond
Benchmarking Drag⋆ for eye direction transformation and beyond Open
Eye direction plays a crucial role in determining the quality of photographs containing human faces. Images where subjects look in inconsistent directions are often perceived as low-quality and discarded. While state-of-the-art deep genera…
View article: Investigating Training Data Detection in AI Coders
Investigating Training Data Detection in AI Coders Open
Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally produce outputs that contain proprietary or sensitive code snippets, raising con…
View article: BURN: Backdoor Unlearning via Adversarial Boundary Analysis
BURN: Backdoor Unlearning via Adversarial Boundary Analysis Open
Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic …
View article: AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches
AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches Open
Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world, revealing detectors' vulnerabilities and risks. However, …
View article: Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning
Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning Open
3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked objects in a scene are replaced with new contents that blend …
View article: A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment Open
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across vario…
View article: Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution Open
The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of fixed-scale SR have been assessed, the robustness of contin…
View article: The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields
The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields Open
Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some …
View article: FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention Open
Face-swapping techniques have advanced rapidly with the evolution of deep learning, leading to widespread use and growing concerns about potential misuse, especially in cases of fraud. While many efforts have focused on detecting swapped f…
View article: Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack Open
Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key t…
View article: Compromising Embodied Agents with Contextual Backdoor Attacks
Compromising Embodied Agents with Contextual Backdoor Attacks Open
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks d…
View article: Event Trojan: Asynchronous Event-based Backdoor Attacks
Event Trojan: Asynchronous Event-based Backdoor Attacks Open
As asynchronous event data is more frequently engaged in various vision tasks, the risk of backdoor attacks becomes more evident. However, research into the potential risk associated with backdoor attacks in asynchronous event data has bee…
View article: MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling
MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling Open
Diffusion-based video generation has achieved significant progress, yet generating multiple actions that occur sequentially remains a formidable task. Directly generating a video with sequential actions can be extremely challenging due to …
View article: Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models Open
Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws befor…
View article: LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks Open
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field, state-of-the-art …
View article: CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection Open
Co-salient object detection (CoSOD) aims to identify the common and salient (usually in the foreground) regions across a given group of images. Although achieving significant progress, state-of-the-art CoSODs could be easily affected by so…
View article: Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models Open
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for highly accessibl…
View article: RUNNER: Responsible UNfair NEuron Repair for Enhancing Deep Neural Network Fairness
RUNNER: Responsible UNfair NEuron Repair for Enhancing Deep Neural Network Fairness Open
Deep Neural Networks (DNNs), an emerging software technology, have achieved impressive results in a variety of fields. However, the discriminatory behaviors towards certain groups (a.k.a. unfairness) of DNN models increasingly become a soc…
View article: AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
AdvGPS: Adversarial GPS for Multi-Agent Perception Attack Open
The multi-agent perception system collects visual data from sensors located on various agents and leverages their relative poses determined by GPS signals to effectively fuse information, mitigating the limitations of single-agent sensing,…
View article: Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack Open
Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the robustn…
View article: TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation Open
Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferability of adversarial examples on semantic segmentation has bee…
View article: DistXplore: Distribution-Guided Testing for Evaluating and Enhancing Deep Learning Systems
DistXplore: Distribution-Guided Testing for Evaluating and Enhancing Deep Learning Systems Open
Deep learning (DL) models are trained on sampled data, where the distribution of training data differs from that of real-world data (i.e., the distribution shift), which reduces the model's robustness. Various testing techniques have been …
View article: Alleviating data insufficiency for Chinese sign language recognition
Alleviating data insufficiency for Chinese sign language recognition Open
Continuous Chinese sign language recognition (CCSLR) methods have shown their strong ability to learn excellent model architectures from datasets. However, due to data insufficiency, it is difficult to complete the CCSLR task. In this work…
View article: Faire: Repairing Fairness of Neural Networks via Neuron Condition Synthesis
Faire: Repairing Fairness of Neural Networks via Neuron Condition Synthesis Open
Deep Neural Networks (DNNs) have achieved tremendous success in many applications, while it has been demonstrated that DNNs can exhibit some undesirable behaviors on concerns such as robustness, privacy, and other trustworthiness issues. A…
View article: Parameter optimization of SVM algorithm for predicting physical parameters of SF6–Cu mixture plasma under local thermodynamic equilibrium
Parameter optimization of SVM algorithm for predicting physical parameters of SF6–Cu mixture plasma under local thermodynamic equilibrium Open
The physical parameters of SF6–Cu mixture plasma are necessary for arc calculation simulation. The calculation of these parameters is very difficult, but the prediction of the corresponding parameters using the existing database is one of …
View article: Fairness via Group Contribution Matching
Fairness via Group Contribution Matching Open
Fairness issues in Deep Learning models have recently received increasing attention due to their significant societal impact. Although methods for mitigating unfairness are constantly proposed, little research has been conducted to underst…
View article: Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection
Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection Open
Detecting the salient objects in a remote sensing image has wide applications for the interdisciplinary research. Many existing deep learning methods have been proposed for Salient Object Detection (SOD) in remote sensing images and get re…
View article: FAIRER: Fairness as Decision Rationale Alignment
FAIRER: Fairness as Decision Rationale Alignment Open
Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues, as deep models typically show distinct accuracy differences among certain subgroups (e.g., males and females). Existing research addresses t…
View article: RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection
RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection Open
The emergence of different sensors (Near-Infrared, Depth, etc.) is a remedy for the limited application scenarios of traditional RGB camera. The RGB-X tasks, which rely on RGB input and another type of data input to resolve specific proble…